Figure 3.
Muscle activity and torso oscillations for the RL agents
We compare muscle activities for two controller types for natural walking with the H0918 model.
(A) The activity for the RL agent has been clipped to 0.5. We use 5 roll-outs of the most natural RL policy and 5 reflex-based controllers that were optimized until convergence. The initial state for the RL agent is randomized, which would cause collapse with the reflex controllers, as they are sensitive to the initial state.
(B) and (C) We show the torso angle with the vertical axis for 5 rollouts of 10 s for the H2190and the MyoLegV0 models for walking and for running. The MyoLegV0 presents stronger lateral oscillations. The dashed line shows a straight torso posture.
